• International Journal of Internet, Broadcasting and Communication
• /
• 제15권4호
• /
• pp.279-293
• /
• 2023

This study investigates network effects to measure how strongly the early adopters affect the brand choice of the potential consumer. By using the Gumbel-Hougaard (GH) copula, this study checks the magnitude of network effects varied from country to country. To consider consumer heterogeneity and network effects in the growth market, this study proposes the multi-brand Gamma/Shifted-Gompertz (m-G/SG) model based on the GH copula. Out of eighteen Western European cellular phone market data and South Korea smartphone data sets, the m-G/SG model provides an improvement in the estimation accuracy over the Libai, Muller, and Peres model. The results show that network effects enhance (i) the polarization of brand choice probabilities as time elapses; (ii) the dominance of the more preferred and the earlier entered brand; and (iii) the deceleration of category-level diffusion. Potential followers can analyze their relationship with earlier entrants through the m-G/SG model and also establish an optimal market entry strategy.

• Journal of the Korean Data and Information Science Society
• /
• 제17권3호
• /
• pp.669-675
• /
• 2006

When using response surface designs, the experimental trials should be carried out in blocks in case of heterogeneity of conditions. When we use nearly orthogonal blocking, we need evaluate the degree of orthogonal blocking. Graphical methods for evaluating the degree of orthogonal blocking are suggested.

• 정보과학회 논문지
• /
• 제45권1호
• /
• pp.61-68
• /
• 2018

암환자의 예후 예측에 기여하는 유전자를 찾는 것은 환자에게 보다 적합한 치료를 제공하기 위한 도전 과제 중 하나이다. 예후 유전자를 찾기 위해 유전자 발현 데이터를 이용한 분류 모델 개발 연구가 많이 이루어지고 있다. 하지만 암의 이질성으로 인해 예후 예측의 정확도 향상에 한계가 있다는 문제가 있다. 본 논문에서는 유방암을 비롯한 6개의 암에 대한 암환자의 마이크로어레이 데이터와 생물학적 네트워크 데이터를 이용하여 페이지랭크 알고리즘을 통해 예후 유전자들을 식별하고, K-Nearest Neighbor 알고리즘을 사용하여 암 환자의 예후를 예측하는 모델을 제안한다. 그리고 페이지랭크를 사용하기 전에 K-Means 클러스터링으로 유전자 발현 패턴이 비슷한 샘플들을 나누어 이질성을 극복하고자 한다. 본 논문에서 제안한 방법은 기존의 유전자 바이오마커를 찾는 알고리즘보다 높은 예측 정확도를 보여 주었으며, GO 검증을 통해 클러스터에 특이적인 생물학적 기능을 확인하였다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2011년도 춘계학술발표대회
• /
• pp.414-415
• /
• 2011

Due to heterogeneity in Data and Processes, healthcare systems are facing the challenge of interoperability. This heterogeneity results in different healthcare workflows of each individual organization. The compatibility of these heterogeneous workflows is possible when standards are followed. HL7 is one of the standards that is used for communicating medical data between healthcare systems. Its newer version V3 is providing semantic interoperability which is lacking in V2. The interoperability in HL7 V3 is only limited to data level and process level interoperability needs to be catered. The process level interoperability is achieved only when heterogeneous workflows are aligned. These workflows are very complex in nature due to continuous change in medical data resulting in problems related to maintenance and degree of automation. Semantic technologies plays important role in resolving the above mentioned problems. This research work is based on the integration of semantic technology in HL7 V3 standard to achieve semantic process interoperability. Web Service Modeling Framework (WSMF) is used for incorporating semantics in HL7 V3 processes and achieves seamless communication. Interaction Ontology represents the process artifacts of HL7 V3 and helps in achieving automation.

• 한국도로학회논문집
• /
• 제16권5호
• /
• pp.133-142
• /
• 2014

PURPOSES : The objective was to develop the advanced method which could not explain each observation's specific characteristic in the present negative binomial method that results in under-estimation of the standard error(t-value inflation) and affects the confidence of whole derived results. METHODS : This study dealt with traffic accidents occurring within interchange segment on highway main line with RPNB(Random Parameter Negative Binomial) method that enables to take account of heterogeneity. RESULTS : As a result, AADT and lighting installation type on the road were revealed to have random parameter and in terms of other geometric variables, all were derived as fixed parameter(same effect on every segment). Also, marginal effects were adapted to analyze the relative effects on traffic accidents. CONCLUSIONS : This study proves that RPNB method which considers each observation's specific characteristics is better fitted to the accident data with geometrics. Thus, it is recommended that RPNB model or other methods which could consider the heterogeneity needs to be adapted in accident analysis.

• 한국암반공학회:학술대회논문집
• /
• 한국암반공학회 2006년도 춘계학술발표회 논문집
• /
• pp.79-93
• /
• 2006

It is well known that acoustic emission (AE) is indicator of rock fracturing or damage as rock is brought to failure under the uniaxial compressive loads. In this paper, an experimental study on the source location of acoustic emission on the cylindrical specimens of granite under uniaxial compression test was made. The AE source location was made by measuring the six channel AE data. Comparing to this experiment, the numerical method is applied to model the initiation and propagation of fracture by AE using a numerical code, RFPA (Realistic Failure Process Analysis). This code incorporates the mesoscopic heterogeneity in Young's modulus and rock strength characteristic of rock masses. In the numerical models, values of Young's modulus and rock strength are realized according to a Weibull distribution in which the distribution parameters represent the level of heterogeneity of the medium. The results of the simulations show that RFPA can be used not only to produce acoustic emission similar to those measurements in our experiments, but also to predict fracturing patterns under uniaxial loading condition.

• The Journal of Asian Finance, Economics and Business
• /
• 제7권4호
• /
• pp.29-39
• /
• 2020

The purpose of this study is to investigate the determinants of blockholder presence in the Korean stock market. This study examines previous theories and studies, points that previous studies did not examine, and proposes two hypotheses. To verify two hypotheses, fundamental data were collected from firms listed on Korea Exchange from 2005 to 2017. As explanatory variables, we use the factors and characteristics of the firms used in the previous studies. Logistic regression analysis was conducted to test the determinants of blockholder presence. We find that firm size is the most distinctive factor determining the presence of blockholder, and firm idiosyncratic risk is the most similar factor determining the existence of each blockholder. Tobin Q shows significant value in family and government, and R&D intensity appears to be a negative related to the presence of blockholder in financial institutions. We also find that the determinant of blockholder presence differs from the mechanisms that govern each individual blockholder type when all blockholders grouped together. This suggests that there is blockholder heterogeneity within Korea listing firms. Our findings contribute to investors and policy makers who interested in the determinants of the presence of blockholder and blockhoder heterogeneity in Korea stock market.

• 대한산업공학회지
• /
• 제42권2호
• /
• pp.96-111
• /
• 2016

Effort to reduce energy consumptions or CO2 emissions is global trend. To follow this trend, spatial studies related to characteristics affecting energy consumptions or CO2 emissions have been conducted, but only with the focus on spatial dependence, not on spatial heterogeneity. The aim of this study is to investigate spatial heterogeneity patterns of CO2 emission based on socio-economic factors, land-use characteristics and traffic infrastructure of Seoul city. Geographically Weighted Regression (GWR) analysis was performed with 423 administrative district data in Seoul. The results suggest that population and employment densities, road density and railway length in most districts are found to have positive impact on the CO2 emissions. Residential and green area densities also have the highest positive impact on CO2 emissions in most districts of Gangnam-gu. The resulting model can be used to identify the spatial patterns of CO2 emissions at district level in Seoul. Eventually it can contribute to local energy policy and planning of metropolitan area.

• 산경연구논집
• /
• 제12권8호
• /
• pp.33-39
• /
• 2021

Purpose: The influence of age on time preference is not identified in the usual cross-sectional analysis. This study aims to test whether age affects time preference after controlling for the effects of individual heterogeneity including cohort effects. Research design, data and methodology: Drawing on a nationally representative panel dataset of Indonesians, we estimate the effects of age on time preference after controlling for unobserved individual heterogeneity as well as potential cohort effects. We measure time preference exploiting information on two sets of multiple price lists: one for a one-year delay, and the other for a five-year delay. Results: When we controlled for time-invariant individual characteristics, including birth cohort effects in a fixed effects model, the older men and women were more patient in a linear fashion, particularly when the delay was longer. To highlight the importance of controlling for individual fixed effects, we repeated the specification without controlling for individual fixed effects in OLS or censored maximum likelihood regression; we found no relation between age and impatience in men or women and for a one or five-year delay. Conclusions: The older men and women are more patient, and time preferences are correlated with unobserved individual heterogeneity.

• 한국전자통신학회논문지
• /
• 제17권5호
• /
• pp.801-808
• /
• 2022

대규모 링크드 데이터에 어떻게 지식을 임베딩하고, 엔티티 매칭을 위해 어떻게 신경망 모델을 적용할 것인가에 대한 연구는 상대적으로 많이 부족한 상황이다. 이에 대한 가장 근본적인 문제는 서로 다른 레이블이 어휘 이질성을 초래한다는 것이다. 본 논문에서는 이러한 어휘 이질성 문제를 해결하기 위해 재정렬 구조를 결합한 확장된 GCN(Graph Convolutional Network) 모델을 제안한다. 제안된 모델은 기존 임베디드 기반 MTransE 및 BootEA 모델과 비교하여 각각 53% 및 40% 성능이 향상되었으며, GCN 기반 RDGCN 모델과 비교하여 성능이 5.1% 향상되었다.